cpuidle: add a sysfs entry to disable specific C state for debug purpose.

Some C states of new CPU might be not good.  One reason is BIOS might
configure them incorrectly.  To help developers root cause it quickly, the
patch adds a new sysfs entry, so developers could disable specific C state
manually.

In addition, C state might have much impact on performance tuning, as it
takes much time to enter/exit C states, which might delay interrupt
processing.  With the new debug option, developers could check if a deep C
state could impact performance and how much impact it could cause.

Also add this option in Documentation/cpuidle/sysfs.txt.

[akpm@linux-foundation.org: check kstrtol return value]
Signed-off-by: ShuoX Liu <shuox.liu@intel.com>
Reviewed-by: Yanmin Zhang <yanmin_zhang@intel.com>
Reviewed-and-Tested-by: Deepthi Dharwar <deepthi@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Len Brown <len.brown@intel.com>

3 files changed, 45 insertions, 1 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 4869b550023..77304b6b8ae 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -245,6 +245,7 @@ static void poll_idle_init(struct cpuidle_driver *drv)
         state->power_usage = -1;
         state->flags = 0;
         state->enter = poll_idle;
+        state->disable = 0;
 }
 #else
 static void poll_idle_init(struct cpuidle_driver *drv) {}
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index ad0952601ae..5c17ca112fc 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -280,7 +280,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
          * We want to default to C1 (hlt), not to busy polling
          * unless the timer is happening really really soon.
          */
-        if (data->expected_us > 5)
+        if (data->expected_us > 5 &&
+                drv->states[CPUIDLE_DRIVER_STATE_START].disable == 0)
                 data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
 
         /*
@@ -290,6 +291,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
         for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
                 struct cpuidle_state *s = &drv->states[i];
 
+                if (s->disable)
+                        continue;
                 if (s->target_residency > data->predicted_us)
                         continue;
                 if (s->exit_latency > latency_req)
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 3fe41fe4851..88032b4dc6d 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -11,6 +11,7 @@
 #include <linux/sysfs.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/capability.h>
 
 #include "cpuidle.h"
 
@@ -222,6 +223,9 @@ struct cpuidle_state_attr {
 #define define_one_state_ro(_name, show) \
 static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL)
 
+#define define_one_state_rw(_name, show, store) \
+static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0644, show, store)
+
 #define define_show_state_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
                          struct cpuidle_state_usage *state_usage, char *buf) \
@@ -229,6 +233,24 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \
         return sprintf(buf, "%u\n", state->_name);\
 }
 
+#define define_store_state_function(_name) \
+static ssize_t store_state_##_name(struct cpuidle_state *state, \
+                const char *buf, size_t size) \
+{ \
+        long value; \
+        int err; \
+        if (!capable(CAP_SYS_ADMIN)) \
+                return -EPERM; \
+        err = kstrtol(buf, 0, &value); \
+        if (err) \
+                return err; \
+        if (value) \
+                state->disable = 1; \
+        else \
+                state->disable = 0; \
+        return size; \
+}
+
 #define define_show_state_ull_function(_name) \
 static ssize_t show_state_##_name(struct cpuidle_state *state, \
                         struct cpuidle_state_usage *state_usage, char *buf) \
@@ -251,6 +273,8 @@ define_show_state_ull_function(usage)
 define_show_state_ull_function(time)
 define_show_state_str_function(name)
 define_show_state_str_function(desc)
+define_show_state_function(disable)
+define_store_state_function(disable)
 
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
@@ -258,6 +282,7 @@ define_one_state_ro(latency, show_state_exit_latency);
 define_one_state_ro(power, show_state_power_usage);
 define_one_state_ro(usage, show_state_usage);
 define_one_state_ro(time, show_state_time);
+define_one_state_rw(disable, show_state_disable, store_state_disable);
 
 static struct attribute *cpuidle_state_default_attrs[] = {
         &attr_name.attr,
@@ -266,6 +291,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
         &attr_power.attr,
         &attr_usage.attr,
         &attr_time.attr,
+        &attr_disable.attr,
         NULL
 };
 
@@ -287,8 +313,22 @@ static ssize_t cpuidle_state_show(struct kobject * kobj,
         return ret;
 }
 
+static ssize_t cpuidle_state_store(struct kobject *kobj,
+        struct attribute *attr, const char *buf, size_t size)
+{
+        int ret = -EIO;
+        struct cpuidle_state *state = kobj_to_state(kobj);
+        struct cpuidle_state_attr *cattr = attr_to_stateattr(attr);
+
+        if (cattr->store)
+                ret = cattr->store(state, buf, size);
+
+        return ret;
+}
+
 static const struct sysfs_ops cpuidle_state_sysfs_ops = {
         .show = cpuidle_state_show,
+        .store = cpuidle_state_store,
 };
 
 static void cpuidle_state_sysfs_release(struct kobject *kobj)